Spelling suggestions: "subject:"selforganising mass"" "subject:"selforganising mas""
1 |
Modelling the development of the retinogeniculate pathwayEglen, Stephen January 1997 (has links)
No description available.
|
2 |
Self organisation and hierarchical concept representation in networks of spiking neuronsRumbell, Timothy January 2013 (has links)
The aim of this work is to introduce modular processing mechanisms for cortical functions implemented in networks of spiking neurons. Neural maps are a feature of cortical processing found to be generic throughout sensory cortical areas, and self-organisation to the fundamental properties of input spike trains has been shown to be an important property of cortical organisation. Additionally, oscillatory behaviour, temporal coding of information, and learning through spike timing dependent plasticity are all frequently observed in the cortex. The traditional self-organising map (SOM) algorithm attempts to capture the computational properties of this cortical self-organisation in a neural network. As such, a cognitive module for a spiking SOM using oscillations, phasic coding and STDP has been implemented. This model is capable of mapping to distributions of input data in a manner consistent with the traditional SOM algorithm, and of categorising generic input data sets. Higher-level cortical processing areas appear to feature a hierarchical category structure that is founded on a feature-based object representation. The spiking SOM model is therefore extended to facilitate input patterns in the form of sets of binary feature-object relations, such as those seen in the field of formal concept analysis. It is demonstrated that this extended model is capable of learning to represent the hierarchical conceptual structure of an input data set using the existing learning scheme. Furthermore, manipulations of network parameters allow the level of hierarchy used for either learning or recall to be adjusted, and the network is capable of learning comparable representations when trained with incomplete input patterns. Together these two modules provide related approaches to the generation of both topographic mapping and hierarchical representation of input spaces that can be potentially combined and used as the basis for advanced spiking neuron models of the learning of complex representations.
|
3 |
Alternative Analysemöglichkeiten geographischer Daten in der Kartographie mittels Self-Organizing MapsKlammer, Ralf 25 August 2011 (has links) (PDF)
Die Kartographie ist eine Wissenschaft, die in ihrem Charakter starke interdisziplinäre Züge aufweist. Sie zeigt sich in den verschiedensten Facetten und wird darum in den unterschiedlichsten Wissenschaften angewandt. Markantester Charakter ist, schon per Definition, die Modellierung von geowissenschaftlichen Ereignissen und Sachverhalten. „A unique facility for the creation and manipulation of visual or virtual representations of geospace – maps – to permit the exploration, analysis, understanding and communication of information about that space.“(ICA 2003) Aus dieser Definition wird die Charakteristik einer Kommunikationswissenschaft (Brassel) deutlich. Gerade seit dem Paradigmenwechsel der 1970er Jahre fließen zahlreiche weitere Aspekte wie Informatik, Semiotik und Psychologie in das Verständnis von Kartographie ein. Dadurch wird die Karte nicht mehr als reines graphisches Mittel verstanden, sondern als Träger und Übermittler von Informationen verstanden. Der Kartennutzer und dessen Verständnis von Karten rücken dabei immer weiter in den Vordergrund und werden „Ziel“ der kartographischen Verarbeitung. Aus diesem Verständnis heraus, möchte ich in der folgenden Arbeit einen relativ neuen Einfluss und Aspekt der Kartographie vorstellen. Es handelt sich um das Modell der Self-Organizing Maps (SOM), welches erstmalig Anfang der 1980er Jahre von Teuvo Kohonen vorgestellt wurde und deshalb auch, von einigen Autoren, als Kohonenmaps bezeichnet wird. Dem Typus nach, handelt es sich dabei um künstliche neuronale Netze, welche dem Nervensystem des menschlichen Gehirns nachempfunden sind und damit allgemein als eine Art selbständiger, maschineller Lernvorgang angesehen werden können. Im Speziellen sind Self-Organizing Maps ein unüberwachtes Lernverfahren, das in der Lage ist völlig unbekannte Eingabewerte zu erkennen und zu verarbeiten. Durch diese Eigenschaft eignen sie sich als optimales Werkzeug für Data Mining sowie zur Visualisierung von hochdimensionalen Daten. Eine Vielzahl von Wissenschaftlern hat diesen Vorteil bereits erkannt und das Modell in ihre Arbeit einbezogen oder auf dessen Verwendbarkeit analysiert. Deshalb möchte in dieser Arbeit, einige dieser Verwendungsmöglichkeiten und den daraus resultierenden Vorteil für die Kartographie aufzeigen.
|
4 |
Alternative Analysemöglichkeiten geographischer Daten in der Kartographie mittels Self-Organizing MapsKlammer, Ralf 21 July 2010 (has links)
Die Kartographie ist eine Wissenschaft, die in ihrem Charakter starke interdisziplinäre Züge aufweist. Sie zeigt sich in den verschiedensten Facetten und wird darum in den unterschiedlichsten Wissenschaften angewandt. Markantester Charakter ist, schon per Definition, die Modellierung von geowissenschaftlichen Ereignissen und Sachverhalten. „A unique facility for the creation and manipulation of visual or virtual representations of geospace – maps – to permit the exploration, analysis, understanding and communication of information about that space.“(ICA 2003) Aus dieser Definition wird die Charakteristik einer Kommunikationswissenschaft (Brassel) deutlich. Gerade seit dem Paradigmenwechsel der 1970er Jahre fließen zahlreiche weitere Aspekte wie Informatik, Semiotik und Psychologie in das Verständnis von Kartographie ein. Dadurch wird die Karte nicht mehr als reines graphisches Mittel verstanden, sondern als Träger und Übermittler von Informationen verstanden. Der Kartennutzer und dessen Verständnis von Karten rücken dabei immer weiter in den Vordergrund und werden „Ziel“ der kartographischen Verarbeitung. Aus diesem Verständnis heraus, möchte ich in der folgenden Arbeit einen relativ neuen Einfluss und Aspekt der Kartographie vorstellen. Es handelt sich um das Modell der Self-Organizing Maps (SOM), welches erstmalig Anfang der 1980er Jahre von Teuvo Kohonen vorgestellt wurde und deshalb auch, von einigen Autoren, als Kohonenmaps bezeichnet wird. Dem Typus nach, handelt es sich dabei um künstliche neuronale Netze, welche dem Nervensystem des menschlichen Gehirns nachempfunden sind und damit allgemein als eine Art selbständiger, maschineller Lernvorgang angesehen werden können. Im Speziellen sind Self-Organizing Maps ein unüberwachtes Lernverfahren, das in der Lage ist völlig unbekannte Eingabewerte zu erkennen und zu verarbeiten. Durch diese Eigenschaft eignen sie sich als optimales Werkzeug für Data Mining sowie zur Visualisierung von hochdimensionalen Daten. Eine Vielzahl von Wissenschaftlern hat diesen Vorteil bereits erkannt und das Modell in ihre Arbeit einbezogen oder auf dessen Verwendbarkeit analysiert. Deshalb möchte in dieser Arbeit, einige dieser Verwendungsmöglichkeiten und den daraus resultierenden Vorteil für die Kartographie aufzeigen.:1.) Einleitung ...........................................................................................2
2.) Aufbau und Funktionsweise von SOM ............................................ 5
2.1.) Was sind Self-Organizing Maps? ................................................5
2.2.) Funktionsweise ............................................................................7
2.3.) Visualisierung des trainierten Kohonen-Netz .......................... 11
2.4.) Software ..................................................................................... 12
3. Möglichkeiten für die Kartographie................................................ 14
3.1 Geowissenschaftliches Data Mining ........................................... 15
3.2 Visualisierung von Daten............................................................. 17
4. explorative Datenanalyse geographischer Daten .......................... 19
4.1 SOM als Geovisualisierung .......................................................... 19
4.1.1 U-Matrix-Darstellung .............................................................22
4.1.2 Projektionen (Netzdarstellungen) ........................................26
4.1.3 2D & 3D-Plots .........................................................................28
4.1.4 Komponentenebenen ...........................................................29
4.2 Geo-SOM & andere Möglichkeiten zur Verarbeitung von
geowissenschaftlichen Daten ................................................... 32
4.2.1 Hierarchische SOMs ...............................................................33
4.2.2 Geo-enforced SOM ................................................................34
4.2.3 Geo-SOM ................................................................................35
4.3 SOM & GIS .................................................................................... 38
5. Datenverarbeitende Anwendungen ............................................... 40
5.1 Klassifizierung von Fernerkundungsdaten................................. 40
5.2 Kantendetektion in Satellitenbildern......................................... 43
5.3 Auswertung von Zeitreihen & Monitoring................................. 47
5.4 Klassifikation von SAR-Daten...................................................... 49
5.5 Generalisierung............................................................................ 50
5.6 Problem des Handlungsreisenden (Travelling Salesman
Problem)..................................................................................... 52
6. SOM als Kartenmetapher zur Visualisierung nicht-geographischer
Daten .............................................................................................. 54
7. Zusammenfassung............................................................................ 62
X. Quellenverzeichnis ........................................................................... 63
X.I Literaturnachweise ....................................................................... 63
X.II Lehrinhalte aus dem Internet ..................................................... 69
X.III Softwarelösungen ...................................................................... 69
|
5 |
Application of supervised and unsupervised learning to analysis of the arterial pressure pulseWalsh, Andrew Michael, Graduate school of biomedical engineering, UNSW January 2006 (has links)
This thesis presents an investigation of statistical analytical methods applied to the analysis of the shape of the arterial pressure waveform. The arterial pulse is analysed by a selection of both supervised and unsupervised methods of learning. Supervised learning methods are generally better known as regression. Unsupervised learning methods seek patterns in data without the specification of a target variable. The theoretical relationship between arterial pressure and wave shape is first investigated by study of a transmission line model of the arterial tree. A meta-database of pulse waveforms obtained by the SphygmoCor"??" device is then analysed by the unsupervised learning technique of Self Organising Maps (SOM). The map patterns indicate that the observed arterial pressures affect the wave shape in a similar way as predicted by the theoretical model. A database of continuous arterial pressure obtained by catheter line during sleep is used to derive supervised models that enable estimation of arterial pressures, based on the measured wave shapes. Independent component analysis (ICA) is also used in a supervised learning methodology to show the theoretical plausibility of separating the pressure signals from unwanted noise components. The accuracy and repeatability of the SphygmoCor?? device is measured and discussed. Alternative regression models are introduced that improve on the existing models in the estimation of central cardiovascular parameters from peripheral arterial wave shapes. Results of this investigation show that from the information in the wave shape, it is possible, in theory, to estimate the continuous underlying pressures within the artery to a degree of accuracy acceptable to the Association for the Advancement of Medical Instrumentation. This could facilitate a new role for non-invasive sphygmographic devices, to be used not only for feature estimation but as alternatives to invasive arterial pressure sensors in the measurement of continuous blood pressure.
|
6 |
Improving Clustering of Gene Expression PatternsJonsson, Per January 2000 (has links)
<p>The central question investigated in this project was whether clustering of gene expression patterns could be done more biologically accurate by providing the clustering technique with additional information about the genes as input besides the expression levels. With the term biologically accurate we mean that the genes should not only be clustered together according to their similarities in expression profiles, but also according to their functional similarity in terms of functional annotation and metabolic pathway. The data was collected at AstraZeneca R&D Mölndal Sweden and the applied computational technique was self-organising maps. In our experiments we used the combination of expression profiles together with enzyme classification annotation as input for the self-organising maps instead of just the expression profiles. The results were evaluated both statistically and biologically. The statistical evaluation showed that our method resulted in a small decrease in terms of compactness and isolation. The biological evaluation showed that our method resulted in clusters with greater functional homogeneity with respect to enzyme classification, functional hierarchy and metabolic pathway annotation.</p>
|
7 |
Application of supervised and unsupervised learning to analysis of the arterial pressure pulseWalsh, Andrew Michael, Graduate school of biomedical engineering, UNSW January 2006 (has links)
This thesis presents an investigation of statistical analytical methods applied to the analysis of the shape of the arterial pressure waveform. The arterial pulse is analysed by a selection of both supervised and unsupervised methods of learning. Supervised learning methods are generally better known as regression. Unsupervised learning methods seek patterns in data without the specification of a target variable. The theoretical relationship between arterial pressure and wave shape is first investigated by study of a transmission line model of the arterial tree. A meta-database of pulse waveforms obtained by the SphygmoCor"??" device is then analysed by the unsupervised learning technique of Self Organising Maps (SOM). The map patterns indicate that the observed arterial pressures affect the wave shape in a similar way as predicted by the theoretical model. A database of continuous arterial pressure obtained by catheter line during sleep is used to derive supervised models that enable estimation of arterial pressures, based on the measured wave shapes. Independent component analysis (ICA) is also used in a supervised learning methodology to show the theoretical plausibility of separating the pressure signals from unwanted noise components. The accuracy and repeatability of the SphygmoCor?? device is measured and discussed. Alternative regression models are introduced that improve on the existing models in the estimation of central cardiovascular parameters from peripheral arterial wave shapes. Results of this investigation show that from the information in the wave shape, it is possible, in theory, to estimate the continuous underlying pressures within the artery to a degree of accuracy acceptable to the Association for the Advancement of Medical Instrumentation. This could facilitate a new role for non-invasive sphygmographic devices, to be used not only for feature estimation but as alternatives to invasive arterial pressure sensors in the measurement of continuous blood pressure.
|
8 |
Improving Clustering of Gene Expression PatternsJonsson, Per January 2000 (has links)
The central question investigated in this project was whether clustering of gene expression patterns could be done more biologically accurate by providing the clustering technique with additional information about the genes as input besides the expression levels. With the term biologically accurate we mean that the genes should not only be clustered together according to their similarities in expression profiles, but also according to their functional similarity in terms of functional annotation and metabolic pathway. The data was collected at AstraZeneca R&D Mölndal Sweden and the applied computational technique was self-organising maps. In our experiments we used the combination of expression profiles together with enzyme classification annotation as input for the self-organising maps instead of just the expression profiles. The results were evaluated both statistically and biologically. The statistical evaluation showed that our method resulted in a small decrease in terms of compactness and isolation. The biological evaluation showed that our method resulted in clusters with greater functional homogeneity with respect to enzyme classification, functional hierarchy and metabolic pathway annotation.
|
9 |
Fog forecasting at Cape Town International Airport : a climatological approachVan Schalkwyk, Lynette 15 February 2012 (has links)
Cape Town International Airport (CTIA) is located along the extreme southern portion of the west coast of South Africa which has the highest frequency of fog in the country. Fog occurs more frequently at CTIA than at any other of the international airports in South Africa. Fog forecasting research in South Africa has largely been neglected and fog forecast verification results show the urgent need for improvement. Accurate fog forecasts are imperative for the aviation industry to prevent costly flight delays and diversions. The main aim of this research is to improve the forecasts of fog at CTIA. The first step towards realising this aim is to provide aviation forecasters with a comprehensive fog climatology that encompasses all aspects of fog: from the seasonal characteristics, to detail regarding the types of fog that frequently occur, synoptic circulations associated with fog and characteristics of the vertical profile of the lower troposphere and boundary layer in which fog forms. Fog types at CTIA are classified by means of an objective hierarchical classification method that takes the formation mechanisms of fog into consideration. Self Organising Maps (SOMs) are used as a synoptic typing method, to determine the synoptic circulations that are most frequently associated with fog at CTIA. Case studies are presented to illustrate the formation mechanisms of 5 different fog types by means of the synoptic circulation, surface observations, satellite imagery and atmospheric soundings. Conclusions drawn from these case studies can assist forecasters with the identification of potential fog events in advance. It is recommended that climatology and case study results be made available to aviation forecasters at CTIA and that similar studies be conducted for all international airports in South Africa that are frequently affected by fog. Copyright / Dissertation (MSc)--University of Pretoria, 2011. / Geography, Geoinformatics and Meteorology / unrestricted
|
10 |
Security Assessment of IoT- Devices Grouped by Similar Attributes : Researching patterns in vulnerabilities of IoT- devices by grouping devices based on which protocols are running. / Säkerhetsbedömning av IoT-Enheter Grupperade efter Liknande EgenskaperSannervik, Filip, Magdum, Parth January 2021 (has links)
The Internet of Things (IoT) is a concept that is getting a lot of attention. IoT devices are growing in popularity and so is the need to protect these devices from attacks and vulnerabilities. Future developers and users of IoT devices need to know what type of devices need extra care and which are more likely to be vulnerable. Therefore this study has researched the correlations between combinations of protocols and software vulnerabilities. Fifteen protocols used by common services over the internet were selected to base the study around. Then an artificial neural network was used to group the devices into 4 groups based on which of these fifteen protocols were running. Publicly disclosed vulnerabilities were then enumerated for all devices in each group. It was found that the percentage of vulnerable devices in each group differed meaning there is some correlation between running combinations of protocols and how likely a device is vulnerable. The severity of the vulnerabilities in the vulnerable devices were also analyzed but no correlation was found between the groups. / Sakernas internet eller Internet of things (IoT) är ett koncept som fått mycket uppmärksamhet. IoT enheter växer drastisk i popularitet, därför är det mer nödvändigt att skydda dessa enheter från attacker och säkerhetsbrister. Framtida utvecklare och användare av IoT system behöver då veta vilka enheter som är mer troliga att ha säkerhetsbrister. Denna studie har utforskat om det finns något samband mellan kombinationer av aktiva protokoll i enheter och säkerhetsbrister. Femton vanligt använda protokoll valdes som bas för studien, ett artificiellt neuralt nätverk användes sedan för att gruppera enheter baserat på dessa protokoll. Kända sårbarheter i enheterna räknades upp för varje grupp. En korrelation mellan kombinationer av protokoll och trolighet för sårbarheter hittades. Allvarlighetsgraden av säkerhetsbristerna i sårbara enheter analyserades också, men ingen korrelation hittades mellan grupperna.
|
Page generated in 0.2468 seconds